Langevin Monte Carlo: Randomized Midpoint Method Revisited
Offered By: Alan Turing Institute via YouTube
Course Description
Overview
Explore the Randomized Midpoint Langevin Monte Carlo (RMP-LCM) method in this 39-minute lecture by Arnak Dalalyan from ENSAE Paris, France. Delve into the efficiency and widespread use of Langevin Monte Carlo for generating random samples from target distributions in high-dimensional Euclidean spaces. Examine various Langevin Monte Carlo variants and understand why RMP-LCM offers the best known non-asymptotic theoretical guarantees on sampling error for target distributions with continuous Lipschitz gradient log-densities. Review existing results, discover extensions, and learn about recent improvements to this powerful sampling technique.
Syllabus
Langevin Monte Carlo Randomised mid point method revisited
Taught by
Alan Turing Institute
Related Courses
Introduction to Bayesian StatisticsDatabricks via Coursera Probability via Computation - Week 4
The Julia Programming Language via YouTube On the Unreasonable Effectiveness of Compressive Imaging - Ben Adcock, Simon Fraser University
Alan Turing Institute via YouTube The Mother of All Representer Theorems for Inverse Problems and Machine Learning - Michael Unser
Alan Turing Institute via YouTube Affine Spline Insights into Deep Learning - Richard Baraniuk, Rice University
Alan Turing Institute via YouTube